tekperson commited on
Commit
836b140
·
verified ·
1 Parent(s): 2a230dd

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. optimizer.pt +1 -1
  4. rng_state.pth +1 -1
  5. scheduler.pt +1 -1
  6. trainer_state.json +67 -171
  7. training_args.bin +2 -2
config.json CHANGED
@@ -30,6 +30,6 @@
30
  "sinusoidal_pos_embds": false,
31
  "tie_weights_": true,
32
  "torch_dtype": "float32",
33
- "transformers_version": "4.42.3",
34
  "vocab_size": 30522
35
  }
 
30
  "sinusoidal_pos_embds": false,
31
  "tie_weights_": true,
32
  "torch_dtype": "float32",
33
+ "transformers_version": "4.44.0",
34
  "vocab_size": 30522
35
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff1db7568c3127f007e7d445a52cdc52ba87e99a11846d62b176dfe791fa0a0f
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffcd681ce3cefc2f3c8d3d78a85c64396a4eab44419e46869799a8fae940cae9
3
  size 267835644
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0ca7acbb2255ca22bcea57c688c3ceda8c0fefaf54a3e463ddec28bfd879939
3
  size 535733434
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49fbfb33c666b7649fdd67e5682bb549cb2bbf660ff7e48f091506e00dce9ccd
3
  size 535733434
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa014fdebae1c328672b43f1bed7673f3bc11f28185785e746fd694a1449df3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4df7e51b4d48400868306673e7f8c6ef3945e0d3ca6fa42b6b3f340d68ad365
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e154de846a6b4884da0f44df50ac2faf21ca208b0eefde73b6f565d13f2f7a60
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898ef30360b27265f9efd50fd1c7231be277ffe1f682927713f07b9b4d126a0f
3
  size 1064
trainer_state.json CHANGED
@@ -1,212 +1,108 @@
1
  {
2
- "best_metric": 2.1997982912580483e-05,
3
- "best_model_checkpoint": "./falcons-finetuned\\checkpoint-1400",
4
- "epoch": 20.0,
5
  "eval_steps": 500,
6
- "global_step": 1400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.9689922480620154,
14
- "eval_loss": 0.1495845764875412,
15
- "eval_runtime": 0.246,
16
- "eval_samples_per_second": 524.39,
17
- "eval_steps_per_second": 134.146,
18
- "step": 70
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_accuracy": 1.0,
23
- "eval_loss": 0.0007492678705602884,
24
- "eval_runtime": 0.2411,
25
- "eval_samples_per_second": 534.954,
26
- "eval_steps_per_second": 136.849,
27
- "step": 140
28
  },
29
  {
30
  "epoch": 3.0,
31
- "eval_accuracy": 1.0,
32
- "eval_loss": 0.0007652111235074699,
33
- "eval_runtime": 0.2424,
34
- "eval_samples_per_second": 532.168,
35
- "eval_steps_per_second": 136.136,
36
- "step": 210
37
  },
38
  {
39
  "epoch": 4.0,
40
- "eval_accuracy": 1.0,
41
- "eval_loss": 0.00015385144797619432,
42
- "eval_runtime": 0.244,
43
- "eval_samples_per_second": 528.687,
44
- "eval_steps_per_second": 135.245,
45
- "step": 280
46
  },
47
  {
48
  "epoch": 5.0,
49
- "eval_accuracy": 1.0,
50
- "eval_loss": 0.00010236301022814587,
51
- "eval_runtime": 0.2299,
52
- "eval_samples_per_second": 561.217,
53
- "eval_steps_per_second": 143.567,
54
- "step": 350
55
  },
56
  {
57
  "epoch": 6.0,
58
- "eval_accuracy": 1.0,
59
- "eval_loss": 7.740984437987208e-05,
60
- "eval_runtime": 0.249,
61
- "eval_samples_per_second": 518.169,
62
- "eval_steps_per_second": 132.555,
63
- "step": 420
64
  },
65
  {
66
  "epoch": 7.0,
67
- "eval_accuracy": 1.0,
68
- "eval_loss": 6.195763126015663e-05,
69
- "eval_runtime": 0.237,
70
- "eval_samples_per_second": 544.304,
71
- "eval_steps_per_second": 139.241,
72
- "step": 490
73
- },
74
- {
75
- "epoch": 7.142857142857143,
76
- "grad_norm": 0.0023473675828427076,
77
- "learning_rate": 3.2142857142857144e-05,
78
- "loss": 0.1216,
79
- "step": 500
80
  },
81
  {
82
  "epoch": 8.0,
83
- "eval_accuracy": 1.0,
84
- "eval_loss": 5.117700857226737e-05,
85
- "eval_runtime": 0.2377,
86
- "eval_samples_per_second": 542.642,
87
- "eval_steps_per_second": 138.815,
88
- "step": 560
89
  },
90
  {
91
  "epoch": 9.0,
92
- "eval_accuracy": 1.0,
93
- "eval_loss": 4.3944502976955846e-05,
94
- "eval_runtime": 0.2422,
95
- "eval_samples_per_second": 532.723,
96
- "eval_steps_per_second": 136.278,
97
- "step": 630
98
  },
99
  {
100
  "epoch": 10.0,
101
- "eval_accuracy": 1.0,
102
- "eval_loss": 3.867461418849416e-05,
103
- "eval_runtime": 0.228,
104
- "eval_samples_per_second": 565.786,
105
- "eval_steps_per_second": 144.736,
106
- "step": 700
107
- },
108
- {
109
- "epoch": 11.0,
110
- "eval_accuracy": 1.0,
111
- "eval_loss": 3.449047653703019e-05,
112
- "eval_runtime": 0.2264,
113
- "eval_samples_per_second": 569.712,
114
- "eval_steps_per_second": 145.74,
115
- "step": 770
116
- },
117
- {
118
- "epoch": 12.0,
119
- "eval_accuracy": 1.0,
120
- "eval_loss": 3.146601375192404e-05,
121
- "eval_runtime": 0.2272,
122
- "eval_samples_per_second": 567.671,
123
- "eval_steps_per_second": 145.218,
124
- "step": 840
125
- },
126
- {
127
- "epoch": 13.0,
128
- "eval_accuracy": 1.0,
129
- "eval_loss": 2.9068054573144764e-05,
130
- "eval_runtime": 0.2295,
131
- "eval_samples_per_second": 562.058,
132
- "eval_steps_per_second": 143.782,
133
- "step": 910
134
- },
135
- {
136
- "epoch": 14.0,
137
- "eval_accuracy": 1.0,
138
- "eval_loss": 2.6998141038347967e-05,
139
- "eval_runtime": 0.2324,
140
- "eval_samples_per_second": 555.063,
141
- "eval_steps_per_second": 141.993,
142
- "step": 980
143
- },
144
- {
145
- "epoch": 14.285714285714286,
146
- "grad_norm": 0.0009529466624371707,
147
- "learning_rate": 1.4285714285714285e-05,
148
- "loss": 0.0001,
149
- "step": 1000
150
- },
151
- {
152
- "epoch": 15.0,
153
- "eval_accuracy": 1.0,
154
- "eval_loss": 2.5497449314570986e-05,
155
- "eval_runtime": 0.2277,
156
- "eval_samples_per_second": 566.436,
157
- "eval_steps_per_second": 144.902,
158
- "step": 1050
159
- },
160
- {
161
- "epoch": 16.0,
162
- "eval_accuracy": 1.0,
163
- "eval_loss": 2.4280441721202806e-05,
164
- "eval_runtime": 0.231,
165
- "eval_samples_per_second": 558.442,
166
- "eval_steps_per_second": 142.857,
167
- "step": 1120
168
- },
169
- {
170
- "epoch": 17.0,
171
- "eval_accuracy": 1.0,
172
- "eval_loss": 2.3132748538046144e-05,
173
- "eval_runtime": 0.2391,
174
- "eval_samples_per_second": 539.505,
175
- "eval_steps_per_second": 138.013,
176
- "step": 1190
177
- },
178
- {
179
- "epoch": 18.0,
180
- "eval_accuracy": 1.0,
181
- "eval_loss": 2.2520083803101443e-05,
182
- "eval_runtime": 0.2403,
183
- "eval_samples_per_second": 536.751,
184
- "eval_steps_per_second": 137.308,
185
- "step": 1260
186
- },
187
- {
188
- "epoch": 19.0,
189
- "eval_accuracy": 1.0,
190
- "eval_loss": 2.213197512901388e-05,
191
- "eval_runtime": 0.232,
192
- "eval_samples_per_second": 556.035,
193
- "eval_steps_per_second": 142.241,
194
- "step": 1330
195
- },
196
- {
197
- "epoch": 20.0,
198
- "eval_accuracy": 1.0,
199
- "eval_loss": 2.1997982912580483e-05,
200
- "eval_runtime": 0.227,
201
- "eval_samples_per_second": 568.281,
202
- "eval_steps_per_second": 145.374,
203
- "step": 1400
204
  }
205
  ],
206
  "logging_steps": 500,
207
- "max_steps": 1400,
208
  "num_input_tokens_seen": 0,
209
- "num_train_epochs": 20,
210
  "save_steps": 500,
211
  "stateful_callbacks": {
212
  "TrainerControl": {
@@ -220,7 +116,7 @@
220
  "attributes": {}
221
  }
222
  },
223
- "total_flos": 184132967823360.0,
224
  "train_batch_size": 4,
225
  "trial_name": null,
226
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.09463215619325638,
3
+ "best_model_checkpoint": "./falcons-finetuned\\checkpoint-222",
4
+ "epoch": 10.0,
5
  "eval_steps": 500,
6
+ "global_step": 370,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.8604651162790697,
14
+ "eval_loss": 0.502533495426178,
15
+ "eval_runtime": 0.3011,
16
+ "eval_samples_per_second": 428.436,
17
+ "eval_steps_per_second": 109.6,
18
+ "step": 37
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_accuracy": 0.9612403100775194,
23
+ "eval_loss": 0.13876038789749146,
24
+ "eval_runtime": 0.2877,
25
+ "eval_samples_per_second": 448.339,
26
+ "eval_steps_per_second": 114.691,
27
+ "step": 74
28
  },
29
  {
30
  "epoch": 3.0,
31
+ "eval_accuracy": 0.9689922480620154,
32
+ "eval_loss": 0.14742323756217957,
33
+ "eval_runtime": 0.3019,
34
+ "eval_samples_per_second": 427.325,
35
+ "eval_steps_per_second": 109.316,
36
+ "step": 111
37
  },
38
  {
39
  "epoch": 4.0,
40
+ "eval_accuracy": 0.9767441860465116,
41
+ "eval_loss": 0.12268275022506714,
42
+ "eval_runtime": 0.292,
43
+ "eval_samples_per_second": 441.765,
44
+ "eval_steps_per_second": 113.01,
45
+ "step": 148
46
  },
47
  {
48
  "epoch": 5.0,
49
+ "eval_accuracy": 0.9767441860465116,
50
+ "eval_loss": 0.12084222584962845,
51
+ "eval_runtime": 0.2757,
52
+ "eval_samples_per_second": 467.823,
53
+ "eval_steps_per_second": 119.676,
54
+ "step": 185
55
  },
56
  {
57
  "epoch": 6.0,
58
+ "eval_accuracy": 0.9767441860465116,
59
+ "eval_loss": 0.09463215619325638,
60
+ "eval_runtime": 0.2864,
61
+ "eval_samples_per_second": 450.424,
62
+ "eval_steps_per_second": 115.225,
63
+ "step": 222
64
  },
65
  {
66
  "epoch": 7.0,
67
+ "eval_accuracy": 0.9844961240310077,
68
+ "eval_loss": 0.10351040214300156,
69
+ "eval_runtime": 0.2903,
70
+ "eval_samples_per_second": 444.346,
71
+ "eval_steps_per_second": 113.67,
72
+ "step": 259
 
 
 
 
 
 
 
73
  },
74
  {
75
  "epoch": 8.0,
76
+ "eval_accuracy": 0.9844961240310077,
77
+ "eval_loss": 0.10580696165561676,
78
+ "eval_runtime": 0.2804,
79
+ "eval_samples_per_second": 460.04,
80
+ "eval_steps_per_second": 117.685,
81
+ "step": 296
82
  },
83
  {
84
  "epoch": 9.0,
85
+ "eval_accuracy": 0.9844961240310077,
86
+ "eval_loss": 0.10663236677646637,
87
+ "eval_runtime": 0.2805,
88
+ "eval_samples_per_second": 459.887,
89
+ "eval_steps_per_second": 117.645,
90
+ "step": 333
91
  },
92
  {
93
  "epoch": 10.0,
94
+ "eval_accuracy": 0.9844961240310077,
95
+ "eval_loss": 0.10691161453723907,
96
+ "eval_runtime": 0.2546,
97
+ "eval_samples_per_second": 506.593,
98
+ "eval_steps_per_second": 129.593,
99
+ "step": 370
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
100
  }
101
  ],
102
  "logging_steps": 500,
103
+ "max_steps": 370,
104
  "num_input_tokens_seen": 0,
105
+ "num_train_epochs": 10,
106
  "save_steps": 500,
107
  "stateful_callbacks": {
108
  "TrainerControl": {
 
116
  "attributes": {}
117
  }
118
  },
119
+ "total_flos": 48351462773760.0,
120
  "train_batch_size": 4,
121
  "trial_name": null,
122
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efadbd5e1933c6ce362e6e03a51217dbfb877d696c9601410a204604ad2b24d5
3
- size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f2081b8bc047ea3b0eb6ad06802ce42204d7d1205dee30a8808d11a152587fb
3
+ size 5176